Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/miyu4u/zido/agents-mdgit clone --depth 1 https://github.com/miyu4u/zidoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/miyu4u/zido/agents-md)<a href="https://agentmods.dev/instructions/miyu4u/zido/agents-md"><img src="https://agentmods.dev/badge/instructions/miyu4u/zido/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02729 | $0.02729 |
| Opus 5 | $0.01365 | $0.01365 |
| Sonnet 5 | $0.00546 | $0.00546 |
| Haiku 4.5 | $0.00273 | $0.00273 |
Grade A, and why
zido AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zido AGENTS.md
PURPOSE
Zido는 Nest CLI workspace 기반의 MCP(Model Context Protocol) server입니다. 여러 지도 API provider를 공통 interface로 감싸 장소 검색과 geocoding 기능을 제공하며, stdio와 HTTP transport를 통해 MCP client에 연결됩니다.
이 문서는 Zido의 runtime ownership, directory structure, 실행 명령어와 변경 후 verification 기준을 정의합니다. 구현 시에는 configuration, provider fallback, place domain, MCP tool registration의 경계를 유지하고, 운영자가 재현할 수 있는 명령어와 검증 절차를 우선합니다.
STRUCTURE
apps: application entryhttp-server: zido http server /mcp transporterstdio: zido stdio servercli: zido cli application
libs: librariescommon: common codes like validator, config ...map-providers: map data API providerskakao: Kakao mapnaver: naver mapgoogle: google map
mcp-runtime: mcp shim moduleplace-domain: place related codes
대표 Flow : apps > (mcp-runtime) > place-domain > map-providers
STRUCTURE GUIDE
- 구조는 stale해지기 쉬우므로 변경이 생기거나 관측상 변경이 있는 경우 STRUCTURE 섹션을 갱신해야합니다.
commonlibrary는config.ts를 configuration의 단일 source of truth로 사용하며 NestConfigurationService와ConfigurationModule을 두지 않습니다.
RULES
- 작업 중 기록된 규칙에 벗어난 pattern을 발견하면, 동일한 pattern이 적용된 범위를 sweep하여 같은 task에서 함께 refactoring해야 한다. (MUST)
- 주의 : 문제가 생겼을 때, git clean revert를 하지 말 것 (변경사항 전체 취소 등)
- tool registration, schema wiring, query-only large-action gating, hook registration을 직접 소유하는 root runtime entrypoint로
src/main.ts를 유지 - 기술 용어, 핵심 용어는 알파벳을 유지하면서 서술은 한국어로 합니다.
- 사용자가 지시한 내용은
AGENTS.md에 기록한 후 해당 규칙에 따라 작업합니다. - 작업 중
AGENTS.md의RULES에 기술된 규칙에서drift또는stale상태인 부분을 발견하면 함께sweep합니다.
GUIDE
HOW TO WRITE COMMENT
- Comment는 multi-line jsdoc 스타일로 해당 함수, 또는 메소드의 이름이 기계적으로 반복되지 않는 의미 있는 주석이어야합니다.
- 작업한 부분 중 const, type, property, function, method에는 multiline jsdoc 형식의 한글 주석을 작성해야합니다.
- comment는 method 또는 const name 의 반복된 서술이여서는 안되며, 구체적인 작동 방식 및 "어떤 역할을 하는지"를 충분히 설명 할 수 있어야합니다.
- property는 각 property에 inline multiline jsdoc으로 작성합니다.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 166 lines · 2,729 tokens per session scan A 81714ed6f6ef
zido AGENTS.md is an instructions file published in the GitHub repository miyu4u/zido (0 stars, last pushed 7d ago), licensed MIT. It adds 2,729 tokens to every session, about $0.0136 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).